Debian Codegraph @

recipes/rmf24_ESKN.recipe

raw
1 #!/usr/bin/env python
2
3 __license__ = 'GPL v3'
4 __copyright__ = '2010, Tomasz Dlugosz <[email protected]>'
5 '''
6 rmf24.pl
7 '''
8
9 import re
10
11 from calibre.web.feeds.news import BasicNewsRecipe
12
13
14 class RMF24_ESKN(BasicNewsRecipe):
15 title = 'Rmf24.pl - Ekonomia Sport Kultura Nauka'
16 description = 'Ekonomia, sport, kultura i nauka ze strony rmf24.pl'
17 language = 'pl'
18 oldest_article = 7
19 max_articles_per_feed = 100
20 __author__ = 'Tomasz D\u0142ugosz'
21 no_stylesheets = True
22 remove_javascript = True
23
24 feeds = [
25 ('Ekonomia', 'http://www.rmf24.pl/ekonomia/feed'),
26 ('Sport', 'http://www.rmf24.pl/sport/feed'),
27 ('Kultura', 'http://www.rmf24.pl/kultura/feed'),
28 ('Nauka', 'http://www.rmf24.pl/nauka/feed'),
29 ]
30
31 keep_only_tags = [dict(name='header', attrs={'class': 'article-header'}), dict(name='div', attrs={'class': 'article-container'})]
32
33 remove_tags = [dict(name='div', attrs={'id': 'ReklamaMobile'}), dict(name='img', attrs={'class': 'img-responsive hidden-lg hidden-md hidden-sm'})]
34
35 extra_css = '''
36 h1 { font-size: 1.2em; }
37 '''
38
39 preprocess_regexps = [
40 (re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1])
41 for i in [
42 (r'<h2>Zdj.cie</h2>', lambda match: ''),
43 (r'<a href="http://www.facebook.com/pages/RMF24pl/.*?>RMF24.pl</a> on Facebook</div>', lambda match: '</div>'),
44 ]
45 ]